app.py

# -*- coding: utf-8 -*-
"""
Created on Thu Jun  8 03:39:02 2023

@author: mritchey
"""

import pandas as pd
import numpy as np
import streamlit as st
from geopy.extra.rate_limiter import RateLimiter
from geopy.geocoders import Nominatim
import folium
from streamlit_folium import st_folium
from vincenty import vincenty

st.set_page_config(layout="wide")

@st.cache_data
def convert_df(df):
    return df.to_csv(index=0).encode('utf-8')

@st.cache_data
def get_data(file='hail2010-20230920_significant_bulk_all.parquet'):
    return pd.read_parquet(file) 


def map_perimeters(address,lat ,lon):

    m = folium.Map(location=[lat, lon],

                    zoom_start=6,
                    height=400)
    folium.Marker(
        location=[lat, lon],
        tooltip=f'Address: {address}',
    ).add_to(m)

    return m

def distance(x):
    left_coords = (x[0], x[1])
    right_coords = (x[2], x[3])
    return vincenty(left_coords, right_coords, miles=True)

def geocode(address):
    try:
        address2 = address.replace(' ', '+').replace(',', '%2C')
        df = pd.read_json(
            f'https://geocoding.geo.census.gov/geocoder/locations/onelineaddress?address={address2}&benchmark=2020&format=json')
        results = df.iloc[:1, 0][0][0]['coordinates']
        lat, lon = results['y'], results['x']
    except:
        geolocator = Nominatim(user_agent="GTA Lookup")
        geocode = RateLimiter(geolocator.geocode, min_delay_seconds=1)
        location = geolocator.geocode(address)
        lat, lon = location.latitude, location.longitude
    return lat, lon





#Side Bar
address = st.sidebar.text_input(
    "Address", "Dallas, TX")
date = st.sidebar.date_input("Loss Date",  pd.Timestamp(2023, 7, 14), key='date')
df_hail=get_data()


#Geocode Addreses
lat, lon = geocode(address)

#Filter DAta
df_hail_cut=df_hail.query(f"{lat}-1<=LAT<={lat}+1 and {lon}-1<=LON<={lon}+1 ")
df_hail_cut=df_hail_cut.query("Date_est<=@date")


df_hail_cut["Lat_address"] = lat
df_hail_cut["Lon_address"] = lon
df_hail_cut['Miles to Hail'] = [
    distance(i) for i in df_hail_cut[['LAT','LON','Lat_address','Lon_address']].values]
df_hail_cut['MAXSIZE'] = df_hail_cut['MAXSIZE'].round(2)

df_hail_cut=df_hail_cut.query("`Miles to Hail`<10")
df_hail_cut['Category']=np.where(df_hail_cut['Miles to Hail']<.25,"At Location",
                                 np.where(df_hail_cut['Miles to Hail']<1,"Within 1 Mile",
                                  np.where(df_hail_cut['Miles to Hail']<3,"Within 3 Miles",       
                                    np.where(df_hail_cut['Miles to Hail']<10,"Within 10 Miles",'Other'))))

df_hail_cut_group=pd.pivot_table(df_hail_cut,index='Date_est',
                                 columns='Category',
                                 values='MAXSIZE',
                                 aggfunc='max')

cols=df_hail_cut_group.columns
cols_focus=['At Location',"Within 1 Mile","Within 3 Miles","Within 10 Miles"]

missing_cols=set(cols_focus)-set(cols)
for c in missing_cols:
    df_hail_cut_group[c]=np.nan
 
df_hail_cut_group2=df_hail_cut_group[cols_focus]  

for i in range(3):
    df_hail_cut_group2[cols_focus[i+1]] = np.where(df_hail_cut_group2[cols_focus[i+1]].fillna(0) <
                                                   df_hail_cut_group2[cols_focus[i]].fillna(0),
                                                   df_hail_cut_group2[cols_focus[i]],
                                                   df_hail_cut_group2[cols_focus[i+1]])



df_hail_cut_group2=df_hail_cut_group2.sort_index(ascending=False)

#Map Data
m = map_perimeters(address,lat, lon)

#Display
col1, col2 = st.columns((3, 2))
with col1:
    st.header('Estimated Maximum Hail Size')
    st.write('Data from 2010 to 2023-09-20')
    df_hail_cut_group2
    csv2 = convert_df(df_hail_cut_group2.reset_index())
    st.download_button(
        label="Download data as CSV",
        data=csv2,
        file_name=f'{address}_{date}.csv',
        mime='text/csv')
with col2:

    st.header('Map')
    st_folium(m, height=400)